Filters








41,369 Hits in 8.5 sec

Transfer Adaptation Learning: A Decade Survey [article]

Lei Zhang, Xinbo Gao
2020 arXiv   pre-print
A research problem is characterized as transfer adaptation learning (TAL) when it needs knowledge correspondence between different moments/domains.  ...  Broader solutions of transfer adaptation learning being created by researchers are identified, i.e., instance re-weighting adaptation, feature adaptation, classifier adaptation, deep network adaptation  ...  ACKNOWLEDGMENT The author would like to thank the pioneer researchers in transfer learning, domain adaptation and other related fields. The author would also like to thank Dr. Mingsheng Long and Dr.  ... 
arXiv:1903.04687v2 fatcat:wurprqieffalnnp6isfkhh5y5i

Domain Adaptation for Visual Applications: A Comprehensive Survey [article]

Gabriela Csurka
2017 arXiv   pre-print
After a general motivation, we first position domain adaptation in the larger transfer learning problem.  ...  Finally, we conclude the paper with a section where we relate domain adaptation to other machine learning solutions.  ...  Domain Adaptation (DA) is a particular case of transfer learning (TL) that leverages labeled data in one or more related source domains, to learn a classifier for unseen or unlabeled data in a target domain  ... 
arXiv:1702.05374v2 fatcat:5va4oz4evjfhxgxddflpbb6pxi

Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation [article]

Jichang Li, Guanbin Li, Yemin Shi, Yizhou Yu
2021 arXiv   pre-print
However, the trained model cannot produce a highly discriminative feature representation for the target domain because the training data is dominated by labeled samples from the source domain.  ...  Pseudo labeling expands the number of "labeled" samples in each class in the target domain, and thus produces a more robust and powerful cluster core for each class to facilitate adversarial learning.  ...  Semi-supervised Domain Adaptation Semi-supervised domain adaptation (SSDA) is a relatively promising form of transfer learning, which intents to leverage a small number of labeled samples (e.g, one or  ... 
arXiv:2104.09415v1 fatcat:lmtocnxxlnd6pahcxgk5oahq7i

Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories [article]

Huanhuan Yu, Menglei Hu, Songcan Chen
2018 arXiv   pre-print
A key ingredient of PA-1SmT is to transfer knowledge through adaptive learning of a common model parameter dictionary, which is completely different from existing popular methods for UDA, such as subspace  ...  Accordingly, for such a new UDA scenario, we propose a UDA framework through the model parameter adaptation (PA-1SmT).  ...  Therefore, we propose a model parameter adaptation framework (PA-1SmT) for this scenario to transfer knowledge through adaptive learning of a common model parameter dictionary, and in turn, use the common  ... 
arXiv:1809.00852v2 fatcat:loowptfrxngcnel3bvj6qrr5jm

Adaptative Balanced Distribution for Domain Adaptation with Strong Alignment

Zhengshan Wang, Xiangjun Wang, Feng Liu, Peipei Gao, Yubo Ni
2021 IEEE Access  
and adding a self-learning network to simultaneously balance them.  ...  Aligning and balancing the marginal and conditional feature distributions are two critical procedures for unsupervised domain adaptation (UDA) problems.  ...  Therefore, domain adaptation methods based on deep learning have become popular these years.  ... 
doi:10.1109/access.2021.3096877 fatcat:wjhrcndtgra3tnx3risvcrcz3m

Class-Incremental Domain Adaptation [article]

Jogendra Nath Kundu, Rahul Mysore Venkatesh, Naveen Venkat, Ambareesh Revanur, R. Venkatesh Babu
2020 arXiv   pre-print
Meanwhile, class-incremental (CI) methods enable learning of new classes in absence of source training data but fail under a domain-shift without labeled supervision.  ...  Existing DA methods tackle domain-shift but are unsuitable for learning novel target-domain classes.  ...  under a domain-shift.  ... 
arXiv:2008.01389v1 fatcat:ukx4f6ohbzgyvo3vo2rvplxjje

Cross domain distribution adaptation via kernel mapping

Erheng Zhong, Wei Fan, Jing Peng, Kun Zhang, Jiangtao Ren, Deepak Turaga, Olivier Verscheure
2009 Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '09  
When labeled examples are limited and difficult to obtain, transfer learning employs knowledge from a source domain to improve learning accuracy in the target domain.  ...  To solve this problem, we propose an adaptive kernel approach that maps the marginal distribution of targetdomain and source-domain data into a common kernel space, and utilize a sample selection strategy  ...  of Computer Science and Engineering at Shanghai Jiao Tong University for sharing the preprocessed Reuters-21578 data set.  ... 
doi:10.1145/1557019.1557130 dblp:conf/kdd/ZhongFPZRTV09 fatcat:mghl6dcxffbgpmygfl34edg5ay

Class-imbalanced Domain Adaptation: An Empirical Odyssey [article]

Shuhan Tan, Xingchao Peng, Kate Saenko
2020 arXiv   pre-print
Towards a better solution, we further proposed a feature and label distribution CO-ALignment (COAL) model with a novel combination of existing ideas.  ...  Unsupervised domain adaptation is a promising way to generalize deep models to novel domains.  ...  Domain Adaptation for Label Shift Despite its wide applicability, learning under label shift remains under-explored.  ... 
arXiv:1910.10320v2 fatcat:muhxzxj74vfc3f6jfqglcetmjq

Generalized Source-free Domain Adaptation [article]

Shiqi Yang, Yaxing Wang, Joost van de Weijer, Luis Herranz, Shangling Jui
2021 arXiv   pre-print
Domain adaptation (DA) aims to transfer the knowledge learned from a source domain to an unlabeled target domain.  ...  Some recent works tackle source-free domain adaptation (SFDA) where only a source pre-trained model is available for adaptation to the target domain.  ...  Acknowledgement We acknowledge the support from Huawei Kirin Solution, and the project PID2019-104174GB-I00 (MINECO, Spain) and RTI2018-102285-A-I00 (MICINN, Spain), Ramón y Cajal fellowship RYC2019-027020  ... 
arXiv:2108.01614v2 fatcat:dixwxo5knneg7bb3g4da4ydonq

DistillAdapt: Source-Free Active Visual Domain Adaptation [article]

Divya Kothandaraman, Sumit Shekhar, Abhilasha Sancheti, Manoj Ghuhan, Tripti Shukla, Dinesh Manocha
2022 arXiv   pre-print
The problem requires adapting a pretrained source domain network to a target domain, within a provided budget for acquiring labels in the target domain, while assuming that the source data is not available  ...  source data for adaptation.  ...  Domain Adaptation Domain adaptation aims to transfer the knowledge learned by a source domain model to an unlabeled target domain.  ... 
arXiv:2205.12840v1 fatcat:ct2hgy3tlfcvlox7t5pd3ovnl4

Lifelong aspect extraction from big data: knowledge engineering

M. Taimoor Khan, Mehr Durrani, Shehzad Khalid, Furqan Aziz
2016 Complex Adaptive Systems Modeling  
Lifelong learning models are tailored for big data having a knowledge module that is maintained automatically.  ...  It includes all supervised, semi-supervised, transfer learning, hybrid and unsupervised techniques having a single target domain known prior to analysis.  ...  Acknowledgements We are thankful to Bahria University, Islambad for providing the necessary environment and support to carry out this work.  ... 
doi:10.1186/s40294-016-0018-7 fatcat:bs5qo3f3lnfb7bwarbvfxxdr2m

Unsupervised Domain Adaptation Through Transferring both the Source-Knowledge and Target-Relatedness Simultaneously [article]

Qing Tian, Yanan Zhu, Chuang Ma, Meng Cao
2021 arXiv   pre-print
Unsupervised domain adaptation (UDA) is an emerging research topic in the field of machine learning and pattern recognition, which aims to help the learning of unlabeled target domain by transferring knowledge  ...  from the source domain.  ...  PA-1SmT PA-1SmT [27] was constructed based on the SLMC model by additionally incorporating cross-domain knowledge transferring terms between the source and target domains, under the assumption that the  ... 
arXiv:2003.08051v3 fatcat:2lqzh2oynrd6xi4cyrximo3xi4

Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation [article]

KwanYong Park, Sanghyun Woo, Inkyu Shin, In So Kweon
2021 arXiv   pre-print
The scheme first clusters compound target data based on style, discovering multiple latent domains (discover).  ...  Finally, target-to-source alignment is learned separately between domains (adapt). In high-level, our solution replaces a hard OCDA problem with much easier multiple UDA problems.  ...  Acknowledgements This work was supported by Samsung Electronics Co., Ltd  ... 
arXiv:2110.04111v1 fatcat:udbcpkspyngvlasaywt5xzczpi

A Survey of Unsupervised Deep Domain Adaptation [article]

Garrett Wilson, Diane J. Cook
2020 arXiv   pre-print
As a complement to this challenge, single-source unsupervised domain adaptation can handle situations where a network is trained on labeled data from a source domain and unlabeled data from a related but  ...  Deep learning has produced state-of-the-art results for a variety of tasks.  ...  Domain Adaptation. One popular type of transfer learning is domain adaptation, which will be the focus of our survey. Domain adaptation is a type of transductive transfer learning.  ... 
arXiv:1812.02849v3 fatcat:paefg5cywbe3tjsp6dffnwkvxy

Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification

Fengxiang Yang, Zhun Zhong, Zhiming Luo, Yuanzheng Cai, Yaojin Lin, Shaozi Li, Nicu Sebe
2021 Zenodo  
Concretely, we propose a Dynamic and Symmetric Cross Entropy loss (DSCE) to deal with noisy samples and a camera-aware meta-learning algorithm (MetaCam) to adapt camera shift.  ...  This paper considers the problem of unsupervised person re-identification (re-ID), which aims to learn discriminative models with unlabeled data.  ...  of changes of clusters and thus promotes the model performance. • We propose a camera-aware meta-learning algorithm (MetaCam) for adapting the shifts caused by cameras.  ... 
doi:10.5281/zenodo.5014558 fatcat:hm4mo4jpandvfk2jfeq2sh26b4
« Previous Showing results 1 — 15 out of 41,369 results